Previous Article in Journal
Smart Postharvest Management of Strawberries: YOLOv8-Driven Detection of Defects, Diseases, and Maturity
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
AgriEngineering
Volume 7
Issue 8
10.3390/agriengineering7080247
agriengineering-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

AIM-Net: A Resource-Efficient Self-Supervised Learning Model for Automated Red Spider Mite Severity Classification in Tea Cultivation

by
Malathi Kanagarajan
1,2,*,
Mohanasundaram Natarajan
1,
Santhosh Rajendran
1,2,
Parthasarathy Velusamy
1,2,
Saravana Kumar Ganesan
2,3,
Manikandan Bose
2,
Ranjithkumar Sakthivel
2 and
Baskaran Stephen Inbaraj
4,*
1
Department of Computer Science Engineering, Karpagam Academy of Higher Education (Deemed University), Coimbatore 641021, India
2
Centre for Artificial Intelligence and Unmanned Aerial Vehicles (CAIUAV), Karpagam Academy of Higher Education (Deemed University), Coimbatore 641102, India
3
Department of Electronics and Communication Engineering, Karpagam College of Engineering, Coimbatore 641032, India
4
Department of Food Science, Fu Jen Catholic University, New Taipei City 242062, Taiwan
*
Authors to whom correspondence should be addressed.
AgriEngineering 2025, 7(8), 247; https://doi.org/10.3390/agriengineering7080247 (registering DOI)
Submission received: 28 May 2025 / Revised: 15 July 2025 / Accepted: 23 July 2025 / Published: 1 August 2025
Versions Notes

Abstract

Tea cultivation faces significant threats from red spider mite (RSM: Oligonychus coffeae) infestations, which reduce yields and economic viability in major tea-producing regions. Current automated detection methods rely on supervised deep learning models requiring extensive labeled data, limiting scalability for smallholder farmers. This article proposes AIM-Net (AI-based Infestation Mapping Network) by evaluating SwAV (Swapping Assignments between Views), a self-supervised learning framework, for classifying RSM infestation severity (Mild, Moderate, Severe) using a geo-referenced, field-acquired dataset of RSM infested tea-leaves, Cam-RSM. The methodology combines SwAV pre-training on unlabeled data with fine-tuning on labeled subsets, employing multi-crop augmentation and online clustering to learn discriminative features without full supervision. Comparative analysis against a fully supervised ResNet-50 baseline utilized 5-fold cross-validation, assessing accuracy, F1-scores, and computational efficiency. Results demonstrate SwAV’s superiority, achieving 98.7% overall accuracy (vs. 92.1% for ResNet-50) and macro-average F1-scores of 98.3% across classes, with a 62% reduction in labeled data requirements. The model showed particular strength in Mild_RSM-class detection (F1-score: 98.5%) and computational efficiency, enabling deployment on edge devices. Statistical validation confirmed significant improvements (p < 0.001) over baseline approaches. These findings establish self-supervised learning as a transformative tool for precision pest management, offering resource-efficient solutions for early infestation detection while maintaining high accuracy.
Keywords: self-supervised learning; red spider mite detection; SwAV; tea cultivation; accuracy; F1-score self-supervised learning; red spider mite detection; SwAV; tea cultivation; accuracy; F1-score

Share and Cite

MDPI and ACS Style

Kanagarajan, M.; Natarajan, M.; Rajendran, S.; Velusamy, P.; Ganesan, S.K.; Bose, M.; Sakthivel, R.; Stephen Inbaraj, B. AIM-Net: A Resource-Efficient Self-Supervised Learning Model for Automated Red Spider Mite Severity Classification in Tea Cultivation. AgriEngineering 2025, 7, 247. https://doi.org/10.3390/agriengineering7080247

AMA Style

Kanagarajan M, Natarajan M, Rajendran S, Velusamy P, Ganesan SK, Bose M, Sakthivel R, Stephen Inbaraj B. AIM-Net: A Resource-Efficient Self-Supervised Learning Model for Automated Red Spider Mite Severity Classification in Tea Cultivation. AgriEngineering. 2025; 7(8):247. https://doi.org/10.3390/agriengineering7080247

Chicago/Turabian Style

Kanagarajan, Malathi, Mohanasundaram Natarajan, Santhosh Rajendran, Parthasarathy Velusamy, Saravana Kumar Ganesan, Manikandan Bose, Ranjithkumar Sakthivel, and Baskaran Stephen Inbaraj. 2025. "AIM-Net: A Resource-Efficient Self-Supervised Learning Model for Automated Red Spider Mite Severity Classification in Tea Cultivation" AgriEngineering 7, no. 8: 247. https://doi.org/10.3390/agriengineering7080247

APA Style

Kanagarajan, M., Natarajan, M., Rajendran, S., Velusamy, P., Ganesan, S. K., Bose, M., Sakthivel, R., & Stephen Inbaraj, B. (2025). AIM-Net: A Resource-Efficient Self-Supervised Learning Model for Automated Red Spider Mite Severity Classification in Tea Cultivation. AgriEngineering, 7(8), 247. https://doi.org/10.3390/agriengineering7080247

Article Metrics

Back to TopTop